© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 141153
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shootout
    -0.26
    å½ĵä½ľ
    -0.26
    å¼ĢäºĨ
    -0.26
    æ¼Ķ
    -0.25
    æ¼ĶåĮĸ
    -0.25
    resp
    -0.24
    å±ķåĩº
    -0.24
    lez
    -0.24
     Trap
    -0.24
    èĽ®
    -0.24
    POSITIVE LOGITS
    个çĻ¾åĪĨ
    0.29
     crumbs
    0.28
    ä¸Ģå®ļ
    0.26
    PV
    0.26
     least
    0.24
    -language
    0.24
     tháºŃp
    0.24
    rão
    0.23
     remainder
    0.23
     flux
    0.23
    Activations Density 0.351%

    No Known Activations

    This feature has no known activations.